ClawHub
Back to skill

Security audit

Autowriter

Security checks for vulnerabilities and agentic risk

Overview

This writing skill is purpose-aligned and limited to user-provided/workspace material, with no executable code or hidden network behavior found.

Before installing, consider whether you want this skill's opinionated first-person, anti-AI writing style. It should only work from sources you provide or files in the current workspace, and it should not browse the web or handle credentials.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The skill mandates 'Use: First person' as a built-in language rule, and similar voice requirements appear elsewhere as hard constraints rather than optional style choices. This imposes a specific communication style on users without any opt-in or alternative, which fits the policy concern around forced language/locale behavior.

Content

No source excerpt is available for this finding.